Den lör 3 dec. 2022 kl 22:52 skrev Sebastian <sebcio.t@xxxxxxxxx>: > > One thing to this discussion. > I had a lot of problems with my clusters. I spent some time debugging. > What I found and what I confirmed on AMD nodes, everything starts working like a charm when I added to kernel param iommu=pt > Plus some other tunings, I can’t share, all information now, but this iommu=pt should help. > On beginning everything looks like something in kernel stack slowdown packets. We're seeing the same on our AMD OSD servers, but we disable iommu in the BIOS, but kernel options probably work as well. For us, nvme drives "get stuck". We think this centos bug is relevant/related, https://bugs.centos.org/view.php?id=17104 -- May the most significant bit of your life be positive. _______________________________________________ ceph-users mailing list -- ceph-users@xxxxxxx To unsubscribe send an email to ceph-users-leave@xxxxxxx
 |